Reconstruction Bottlenecks in Object-Centric Generative Models

Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of "reconstruction bottlenecks" for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment